Open ASR Leaderboard adds Egyptian and Nigerian accent data
Understand the story
On November 6, 2026, Hugging Face announced on its official blog a partnership with Liva AI to add two private datasets to the Open ASR Leaderboard: conversational speech in Egyptian English (1.34 hours) and Nigerian English (1.55 hours). The annotations in these datasets include punctuation, casing, and disfluencies, expanding the leaderboard's evaluation coverage of different English accents. This update enables the Open ASR Leaderboard, beyond its existing evaluation data, to also evaluate speech recognition for Egyptian and Nigerian English accents. The above is all that has been reported so far; no further developments are available.
AI overview of reporting · Updated 1 h前
Reporting timeline
Explore different aspects of the story through its reporting.
- Hugging Face BlogEgyptian and Nigerian English join the Open ASR Leaderboard
Hugging Face partnered with Liva AI to add two private datasets to the Open ASR Leaderboard: Egyptian English (1.34 hours) and Nigerian English (1.55 hours) conversational speech, annotated with punctuation, casing, and disfluencies.
Story heat trend
Not enough continuous observations to show a trend yet.